How should AI systems behave, and who should decide?
How should AI systems behave, and who should decide?
How should AI systems behave, and who should decide?
Interfaces for exploring transformer language models by looking at input saliency and neuron activation. Explorable #1: Input saliency of a list of countries generated by a language model Tap or hover over the output tokens: Explorable #2: Neuron activation analysis reveals four groups of neurons, each is associated with generating a certain type of token Tap or hover over the sparklines on the left to isolate a certain factor: The Transformer architecture has been powering a number of the recent advances in NLP. A breakdown of this architecture is provided here . Pre-trained language models based on the architecture, in both its auto-regressive (models that use their own output as input to next time-steps and that process tokens from left-to-right, like GPT2) and denoising (models trained by corrupting/masking the input and that process tokens bidirectionally, like BERT) variants continue to push the envelope in various tasks in NLP and, more recently, in computer vision. Our understanding of why these models work so well, however, still lags behind these developments. This exposition series continues the pursuit to interpret and visualize the inner-workings of transformer-based language models. We illustrate how some key interpretability methods apply to transformer-based language models. This article focuses on auto-regressive models, but these methods are applicable to other architectures and tasks as well. This is the first article in the series. In it, we present explorables and visualizations aiding the intuition of: Input Saliency methods that score input tokens importance to generating a token. Neuron Activations and how individual and groups of model neurons spike in response to inputs and to produce outputs. The next article addresses Hidden State Evolution across the layers of the model and what it may tell us about each layer’s role.
In this episode of Open Source Directions, we were joined by Thomas Wiecki once again who talked about the work being done with PyMC. PyMC3 is a Python package for Bayesian statistical modeling and Probabilistic Machine Learning focusing on advanced Markov chain Monte Carlo (MCMC) and variational inference (VI) algorithms. Its flexibility and extensibility make it applicable to a large suite of problems.
In this episode, we have an engaging and very entertaining discussion with Jono Bacon, the founder of Jono Bacon Consulting. Jono was Director of Community at notable companies such as Github, Canonical, and XPRIZE. He is one of the top (if not the top) experts in the world when it comes to building strong communities.
In this episode of Open Source Directions we were joined by Matthew Seal who talked about the work he has been doing with Jupyter and Nteract. Matthew also discussed a particular topic: common Jupyter tools and their adoption for various use cases in the wild.
In this episode, we have a great conversation with Patrick Masson, the General Manager of Open Source Initiative (OSI). Patrick is an expert at developing and managing highly distributed organizations.